Chris Wikle

View Calendar
March 22, 2021 11:30 am - 12:30 pm

Adapting Efficient Reservoir Neural Methods for Statistical Long-Lead Forecasting of Ecological Processes

If it is so difficult to forecast the weather a few days from now, how can we forecast the state of weather-sensitive ecological systems one year out? The atmosphere is a chaotic dynamical system, and because of that, skillful weather forecasts are only possible out to about 7 to 10 days.  However, dynamical processes in the ocean operate on a much longer time scales, and many atmospheric processes depend crucially on the ocean as a forcing mechanism.  Some of these processes can be forced remotely, leading to so-called teleconnections.  This coupling between the slowly varying ocean and the faster varying atmosphere and associated processes, allows for the skillful prediction of some general properties of such systems many months in advance.  These long-lead forecasts are important for activities such as agricultural and wildlife management, energy production, and disaster planning, to name a few.  It has consistently been established that statistical models can provide some of the most skillful long-lead forecasts. However, it can be particularly challenging to specify parameterizations for nonlinear dynamical spatio-temporal forecast models that are simultaneously useful scientifically and efficient computationally, and that allow for proper uncertainty quantification.  In some cases, when such information is available, one can embed mechanistic information into multi-level (deep/hierarchical) models to facilitate parameter reduction and interpretability.  When such information is not available (such as with animal behavior) then alternative learning strategies such as deep neural models can be applied.  One challenge with such methods can be uncertainty quantification and the necessity of having very large data sets for model training.  Here I present an approach where we have integrated an alternative efficient “AI” spatio-temporal dynamical model, a deep echo state network, in a statistical framework to accommodate uncertainty quantification. This is applied to long-lead (one-year ahead) forecasting of settling patterns of Northern Pintails (Anas acuta) in the Prairie Pothole region of North America.

Related upcoming events

  • August 23, 2021 11:30 am - August 23, 2021 12:30 pm

    SUNY ESF

    Uncertainty analysis for ecosystem studies

  • August 30, 2021 11:30 am - August 30, 2021 12:30 pm

    NAU Marketing

    Photography in the Field

  • September 6, 2021 All day
    No additional details for this event.
  • September 13, 2021 11:30 am - September 13, 2021 12:30 pm

    Senior Director, Data Leadership, AGU

    FAIR and Open Data

  • September 20, 2021 11:30 am - September 20, 2021 12:30 pm

    NASA Goddard

  • September 27, 2021 11:30 am - September 27, 2021 12:30 pm

    NCAR

  • October 4, 2021 11:30 am - October 4, 2021 12:30 pm

    School of the Art Institute of Chicago

  • October 11, 2021 11:30 am - October 11, 2021 12:30 pm

    University of Oxford

  • October 18, 2021 11:30 am - October 18, 2021 12:30 pm

    University of Arizona

  • October 25, 2021 11:30 am - October 25, 2021 12:30 pm

    Florida International University